A dynamic energy management method and system based on wave energy power generation data

Abstract

The application discloses a kind of dynamic energy management method and system based on wave energy power generation data, S1.wave energy power generation dataset is obtained;S2.wave periodicity feature data and fluctuation trend data are generated;S3.load demand model is generated, and the priority of current load demand is evaluated;S4.based on dynamic load demand evaluation result, energy distribution is carried out to wave energy power generation system using improved bitterfish optimization algorithm, and energy storage scheduling plan and load scheduling plan are generated;S5.combining energy storage scheduling plan and load scheduling plan, one of energy storage priority mode, output priority mode or hybrid mode is selected, and the energy output of wave energy power generation system is dynamically adjusted under the selected mode;S6.according to current wave energy power generation data and load demand model, the charging and discharging operation of energy storage device is controlled.The application has greatly improved in fluctuation adaptability and complex scene load coverage, meets the demand of modern marine energy application scene.

Description

Technical Field

[0001] This invention relates to the field of power generation technology, and in particular to a dynamic energy management method and system based on wave energy power generation data. Background Technology

[0002] With the growth of global energy demand and the continuous development of renewable energy technologies, wave energy power generation, as a clean energy technology with great potential, has received widespread attention. Wave energy has the characteristics of high energy density and sustainability, and can continuously capture and convert energy in the marine environment to provide a reliable energy supply for coastal areas.

[0003] Currently, most wave energy generation systems employ a single strategy or fixed mode for energy management, such as directly supplying power to the load or buffering through simple energy storage devices. Existing technologies primarily focus on wave energy capture and improving power generation efficiency, while paying less attention to handling power generation fluctuations and dynamically matching them with load demand. Current energy management methods typically rely on simple rule-based algorithms for static matching of wave energy generation and load demand, lacking adaptability to periodic and random wave fluctuations. Furthermore, existing technologies suffer from the following significant problems: First, due to the periodic and random variations in wave energy, traditional energy management methods struggle to effectively suppress power generation fluctuations, easily leading to power supply instability and energy waste. Second, existing energy storage system control strategies do not fully consider the real-time dynamic relationship between power generation and load demand, preventing energy storage systems from achieving optimal performance under high volatility conditions. Third, the single mode of energy allocation fails to meet the needs of complex load scenarios, unable to flexibly switch between energy storage priority, output priority, and hybrid modes. Finally, traditional energy management systems rely heavily on fixed rules and static models, lacking intelligent and dynamic optimization capabilities, making it difficult to adapt to complex ocean wave environments and changing load demands.

[0004] In summary, existing dynamic energy management methods for wave energy generation have significant shortcomings in terms of energy allocation flexibility, system efficiency improvement, and adaptability to wave energy instability. The problems with existing technologies limit the promotion and efficiency improvement of wave energy generation systems in practical application scenarios. There is an urgent need for an intelligent and dynamic energy management method and system to overcome the above-mentioned technical difficulties. Summary of the Invention

[0005] One objective of this invention is to propose a dynamic energy management method and system based on wave energy power generation data. This invention significantly improves both the volatility adaptability and load coverage in complex scenarios, meeting the needs of modern marine energy application scenarios.

[0006] A dynamic energy management method based on wave energy generation data according to an embodiment of the present invention includes the following steps:

[0007] S1. Obtain the wave energy power generation dataset and transmit the wave energy power generation dataset to the edge computing device for preprocessing;

[0008] S2. The preprocessed wave energy power generation dataset is transmitted to the central control system through a communication network, and the wave energy power generation data is classified, stored and analyzed to generate wave periodicity characteristic data and fluctuation trend data.

[0009] S3. Based on real-time power generation data, wave periodicity characteristic data, and fluctuation trend data, combined with load demand data and energy storage device status, generate a load demand model and assess the priority of current load demand;

[0010] S4. Based on the dynamic load demand assessment results, the improved bitter fish optimization algorithm is used to allocate energy to the wave energy power generation system and generate energy storage scheduling plan and load scheduling plan;

[0011] S5. Combining the energy storage dispatch plan and the load dispatch plan, select one of the following modes: energy storage priority mode, output priority mode, or hybrid mode, and dynamically adjust the energy output of the wave energy power generation system in the selected mode;

[0012] S6. Control the charging and discharging operations of the energy storage device based on the current wave energy generation data and load demand model, and adjust the operating status of the energy storage device in real time.

[0013] Optionally, S1 includes the following steps:

[0014] S11. Obtain wave characteristic data D by using ocean wave sensors deployed in the wave energy power generation system;

[0015] S12. The power generation data P is recorded in real time by the monitoring device on the wave energy power generation device. t ;

[0016] S13. Obtain load demand data L through the load monitoring system. t ;

[0017] S14 constructs a wave energy power generation dataset, which time-series correlates wave characteristic data, real-time power generation data, and load demand data, forming a unified wave energy power generation dataset indexed by timestamps:

[0018] D = {D w ,P t ,L t};

[0019] S15 inputs the constructed wave energy power generation dataset D into the edge computing device for data cleaning, noise reduction, and formatting to generate a preprocessed wave energy power generation dataset:

[0020]

[0021] in, This represents the wave characteristics data after cleaning and noise reduction. This represents the real-time power generation data after cleaning and noise reduction. This represents the load demand data after cleaning and noise reduction.

[0022] Optionally, S2 includes the following steps:

[0023] S21. Transmit the preprocessed wave energy generation dataset through a communication network. Data is transmitted from edge computing devices to the central control system;

[0024] S22, Wave energy generation data transmitted to the central control system The wave energy generation dataset is categorized and stored, and then allocated to the storage module:

[0025]

[0026] Among them, M i S represents the storage module number to which the i-th data record is allocated. j This represents the data feature space of storage module j, where j = 1, 2, 3 correspond to wave characteristic data, real-time power generation data, and load demand data, respectively. w represents the i-th data record. j The weight parameters of storage module j depend on the current module's load capacity and response priority;

[0027] S23, Based on wave characteristic data Wave periodicity characteristic data C is extracted using time series analysis. w ={T c H c}:

[0028]

[0029] Among them, T c The primary period of a wave is represented by its frequency ω. k The reciprocal of H is obtained. c Indicates the main wave height, expressed as wave height H. k The root mean square value is calculated, where N represents the total number of samples in the wave characteristic data, and ω k and H kThese are the frequency and wave height of the k-th wave, respectively;

[0030] S24, Based on real-time power generation data Calculate power generation fluctuation trend data B using statistical analysis methods. p ={μ p ,σ p}:

[0031]

[0032] Where, μ p σ represents the average value of electricity generated. p P(t) represents the fluctuation range of power generation, P(t) represents the real-time power generation at time t, and T represents the total time length of power generation data recording.

[0033] Optionally, S3 includes the following steps:

[0034] S31. Construct a power generation supply model G(t) using real-time power generation data, wave periodicity characteristic data, and fluctuation trend data:

[0035]

[0036] Where G(t) represents the power generation supply capacity at time t, α, β, γ are weighting factors used to balance the impact of real-time power generation, wave periodicity characteristics, and power generation fluctuation trends on the power generation supply model, and H c and T c These represent the main wave height and main period, respectively, σ p This refers to the fluctuation range of power generation.

[0037] S32. Construct a load demand model L(t) by combining load demand data and energy storage device status data:

[0038]

[0039] Where L(t) represents the actual load demand at time t, E c E represents the current remaining energy of the energy storage device. m E represents the maximum capacity of the energy storage device. m This is an energy storage impact factor used to reflect the ability of energy storage devices to reduce load demand.

[0040] S33. Calculate the load demand priority P based on the power generation supply model G(t) and the load demand model L(t). l (t):

[0041]

[0042] Among them, P l(t) represents the load demand priority at time t, and ∈ is a positive decimal to prevent the denominator from being zero;

[0043] S34, Prioritize load demand P l (t) Classify according to the preset priority threshold θ to form a load priority list P. list :

[0044] P list ={(t i ,P l (t i ))∣P l (t i )≥θ};

[0045] Among them, P list t represents the set of load demand items whose priority meets the threshold. i θ represents the time point i, and θ represents the minimum threshold for priority, used to filter high-priority load demands.

[0046] Optionally, S4 includes the following steps:

[0047] S41, Based on the load demand priority list P list Establish a multi-objective optimization function F based on the real-time power generation supply capacity G(t). multi The multi-objective optimization function minimizes the impact of fluctuations and energy storage operating costs, while simultaneously optimizing load coverage.

[0048]

[0049] Among them, F multi The sum of the multi-objective optimization function is represented by w1, w2, and w3, which are weighting factors of the optimization objectives, used to balance supply and demand errors, energy storage costs, and load coverage. a(t) represents the proportion of power generation allocated to the load at time t. out (t) represents the discharge power of the energy storage device at time t, S in (t) represents the charging power of the energy storage device at time t;

[0050] S42. Design a dynamic weight adjustment mechanism to dynamically adjust the weight factors of the optimization function based on load demand priority and power generation fluctuation trend data:

[0051]

[0052] Wherein, κ1, κ2, κ3 are the initial weighting factors;

[0053] S43. Initialize the population solution using the bitter fish optimization algorithm, including the power generation allocation ratio a(t) and the energy storage device discharge power S. out (t) and the charging power S of the energy storage devicein (t), and introduce a fluctuation sensitivity factor φ(t) to enhance the diversity of population solutions:

[0054]

[0055] The population solution is initialized as follows:

[0056] a i (t)=φ(t)·rand(0,1);

[0057]

[0058] Where φ(t) represents the fluctuation sensitivity factor, which adjusts the search range of the population solution based on wave periodicity and fluctuation amplitude, and rand(a,b) represents the random number generated in the interval [a,b].

[0059] S44. Perform global search and local optimization on the initialized population solution, and trigger population reconstruction during periods of high volatility based on the jumping mechanism of the bitter fish algorithm:

[0060]

[0061] Where randn(μ, σ) represents a Gaussian random variable with mean μ and standard deviation σ;

[0062] Population reconstruction dynamically adjusts the search direction through a fluctuation-sensitive factor φ(t);

[0063] S45. The iterative update and optimization results ultimately yield the optimal power generation allocation ratio a. * (t), Discharge power of energy storage device and energy storage device charging power Based on the optimization results, energy storage scheduling plans and load scheduling plans are generated.

[0064] Optionally, S5 includes the following steps:

[0065] S51, Based on Energy Storage Dispatch Plan The optimal result of the load scheduling plan a * (t), defining the selection criteria for energy storage priority mode, output priority mode, and hybrid mode:

[0066]

[0067] Where M(t) represents the mode selection at time t, 1 is the energy storage priority mode, 2 is the output priority mode, 3 is the hybrid mode, and δ is the energy storage state threshold, which represents the key value of the charging state of the energy storage device, and its range is [0,1].

[0068] S52. In the energy storage priority mode, the wave energy power generation system prioritizes charging the energy storage device and dynamically adjusts the power generation supply ratio.

[0069] S53. In the output priority mode, the wave energy power generation system prioritizes meeting the load demand and uses energy storage devices to supplement the insufficient power supply.

[0070] S54. In hybrid mode, the wave energy power generation system meets the load demand while using the remaining power generation capacity to charge the energy storage device and dynamically adjusts the power generation distribution.

[0071] Optionally, S6 includes the following steps:

[0072] S61. Calculate the target charging and discharging power S of the energy storage device based on wave energy generation data G(t) and load demand model L(t). target (t):

[0073]

[0074] Among them, S target (t) represents the target charging and discharging power of the energy storage device at time t, E c and E m These represent the current remaining energy and maximum capacity of the energy storage device, respectively.

[0075] S62. Calculate the actual charging and discharging power S based on the operating status of the energy storage device. actual (t):

[0076]

[0077] Among them, S actual (t) represents the actual charging and discharging power of the energy storage device at time t, R in} represents the maximum charging rate of the energy storage device, R out This indicates the maximum discharge rate of the energy storage device;

[0078] S63. Update the operating status of the energy storage device, including the current remaining energy E. c and charge / discharge modes:

[0079]

[0080] in, M represents the remaining energy of the energy storage device at the next moment, Δt represents the time interval, and M represents the energy of the device at the next moment. s (t) represents the charging and discharging mode of the energy storage device, where 1 is the charging mode, -1 is the discharging mode, and 0 is the standby mode;

[0081] S64. Monitor the operating status of the energy storage device in real time and adjust the operating strategy based on the anomaly detection mechanism:

[0082] like Then the charging power is limited;

[0083] like This limits the discharge power.

[0084] A dynamic energy management system based on wave energy generation data, used to execute a dynamic energy management method based on wave energy generation data, includes the following modules:

[0085] The wave energy data acquisition module is used to acquire wave characteristic data, real-time power generation data, and load demand data through a sensor network, and upload them to the edge computing device in real time to complete data preprocessing, including data cleaning, noise reduction, and formatting, to generate a preprocessed wave energy power generation dataset.

[0086] The data transmission and storage module transmits the pre-processed wave energy power generation dataset to the central control system through a communication network, and classifies and stores the data, including wave characteristic data storage, power generation data storage and load demand data storage.

[0087] The data analysis and feature extraction module is used to analyze the stored data, extract wave periodicity feature data and fluctuation trend data, and generate a power generation characteristic model and its dynamic change trend.

[0088] The load demand assessment module combines real-time power generation data, wave periodicity characteristic data, and fluctuation trend data with load demand data and energy storage device status data to calculate and generate a load demand model. It also dynamically assesses the priority of load demand and forms a priority list.

[0089] The optimization scheduling module uses the "bitter fish" optimization algorithm to allocate energy to the wave energy power generation system based on the load demand priority list, calculates the energy storage scheduling plan and the load scheduling plan, and dynamically adjusts the parameters of the optimization algorithm to adapt to the periodic and random changes of wave energy.

[0090] The mode selection module, in conjunction with the energy storage scheduling plan and the load scheduling plan, selects the optimal mode from the energy storage priority mode, output priority mode or hybrid mode based on the energy storage device status and power generation capacity, and dynamically adjusts the proportion of energy output.

[0091] The energy storage operation control module controls the charging and discharging operations of the energy storage device based on real-time wave energy generation data and load demand model, and adjusts its charging and discharging power according to the operating status of the energy storage device to avoid overcharging or over-discharging, while ensuring the operation of the energy storage device under different load demands.

[0092] The real-time monitoring and feedback module monitors the operating status of the wave energy power generation system, energy storage device and load equipment in real time, collects feedback data and transmits it to the optimization scheduling module and mode selection module, dynamically adjusts the energy management strategy, and forms a closed-loop control of the system.

[0093] The system coordination and communication module is used to coordinate the operating status of wave energy generation devices, energy storage devices, and load equipment, and to ensure real-time data exchange and collaborative computing between the modules through communication protocols.

[0094] The beneficial effects of this invention are:

[0095] (1) The present invention adopts an improved bitter fish optimization algorithm, which combines the periodic characteristics and random fluctuation characteristics of wave energy power generation. Through the introduction of dynamic weight adjustment mechanism and fluctuation sensitive factor, it realizes the efficient matching between power generation supply and load demand. The improved bitter fish optimization algorithm can dynamically adjust the energy distribution strategy according to the real-time changes of wave energy data, which significantly reduces the impact of supply and demand imbalance on system stability under complex wave conditions. At the same time, it supports flexible switching between energy storage priority, output priority and hybrid mode, ensuring that the system can operate efficiently in various application scenarios.

[0096] (2) This invention constructs a complete dynamic feedback closed-loop control system through the charging and discharging control and real-time operation status monitoring of the energy storage device. Through real-time evaluation of the load demand model and dynamic adjustment of the priority list, combined with the execution of the energy storage scheduling plan and the load scheduling plan, the precise linkage between the energy storage device and the power generation system is realized. Compared with the traditional energy storage control strategy, this invention can adjust the charging and discharging mode of the energy storage device according to real-time data, effectively avoid the overcharging or over-discharging problem of the energy storage device, and optimize the operating efficiency of the energy storage system.

[0097] (3) The present invention constructs an integrated energy management system architecture that includes data acquisition, transmission, storage, analysis and scheduling. It can capture wave energy characteristic data, power generation data and load demand data in real time and generate high-precision power supply model and load demand model. Through the intelligent analysis module and optimization scheduling module of the central control system, it can quickly generate energy storage scheduling plan and load scheduling plan, and optimize energy allocation by combining the dynamic mode selection module. The data-driven architecture enables the system to respond quickly to the fluctuation changes of wave energy power generation, improve the decision efficiency and accuracy of energy allocation, and greatly improve the volatility adaptability and load coverage of complex scenarios, thus meeting the needs of modern marine energy application scenarios. Attached Figure Description

[0098] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0099] Figure 1 The flowchart shows a dynamic energy management method and system based on wave energy power generation data proposed in this invention. Detailed Implementation

[0100] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, illustrating only the basic structure of the invention, and therefore only show the components relevant to the invention.

[0101] refer to Figure 1 A dynamic energy management method based on wave energy generation data includes the following steps:

[0102] S1. Obtain the wave energy power generation dataset and transmit the wave energy power generation dataset to the edge computing device for preprocessing;

[0103] S2. The preprocessed wave energy power generation dataset is transmitted to the central control system through a communication network, and the wave energy power generation data is classified, stored and analyzed to generate wave periodicity characteristic data and fluctuation trend data.

[0104] S3. Based on real-time power generation data, wave periodicity characteristic data, and fluctuation trend data, combined with load demand data and energy storage device status, generate a load demand model and assess the priority of current load demand;

[0105] S4. Based on the dynamic load demand assessment results, the improved bitter fish optimization algorithm is used to allocate energy to the wave energy power generation system and generate energy storage scheduling plan and load scheduling plan;

[0106] S5. Combining the energy storage dispatch plan and the load dispatch plan, select one of the following modes: energy storage priority mode, output priority mode, or hybrid mode, and dynamically adjust the energy output of the wave energy power generation system in the selected mode;

[0107] S6. Control the charging and discharging operations of the energy storage device based on the current wave energy generation data and load demand model, and adjust the operating status of the energy storage device in real time.

[0108] In this embodiment, S1 includes the following steps:

[0109] S11. Obtain wave characteristic data D by using ocean wave sensors deployed in the wave energy power generation system;

[0110] S12. The power generation data P is recorded in real time by the monitoring device on the wave energy power generation device. t ;

[0111] S13. Obtain load demand data L through the load monitoring system. t ;

[0112] S14 constructs a wave energy power generation dataset, which time-series correlates wave characteristic data, real-time power generation data, and load demand data, forming a unified wave energy power generation dataset indexed by timestamps:

[0113] D = {D w ,P t ,L t};

[0114] S15 inputs the constructed wave energy power generation dataset D into the edge computing device for data cleaning, noise reduction, and formatting to generate a preprocessed wave energy power generation dataset:

[0115]

[0116] in, This represents the wave characteristics data after cleaning and noise reduction. This represents the real-time power generation data after cleaning and noise reduction. This represents the load demand data after cleaning and noise reduction.

[0117] Equipment Name: Ocean Wave Sensor;

[0118] Function: Collects periodic wave characteristic data such as wave frequency, wave height, and period;

[0119] Model: AWS-900 (Acoustic wave sensor, compliant with ISO 19901 marine standard);

[0120] The core parameters include:

[0121] Measurement parameters: Wave height (significant wave height): 0.1–30 meters; Wave period: 1–30 seconds; Wave frequency: 0.03–1 Hz; Wave direction: 0–360 degrees (1 degree resolution);

[0122] Accuracy: Wave height ±3%FS (typical); Period ±0.2 seconds;

[0123] Sampling frequency: 1Hz (configurable up to 5Hz);

[0124] Communication interfaces: Wired: RS485 (Modbus RTU); Wireless: Beidou short message (suitable for sea areas without base stations);

[0125] Power supply: Solar power + lithium battery (lasts ≥15 days in continuous cloudy / rainy weather);

[0126] Environmental adaptability: Working depth: 0-50 meters (underwater installation); Waterproof rating: IP68 (long-term immersion); Salt spray resistance: Complies with GB / T10110-2005 standard; Deployment method: Installed on the bottom of the wave energy power generation device float, and transmits data to the central control system via cable or wirelessly.

[0127] Equipment Name: Integrated Monitoring Module for Wave Energy Generation Device;

[0128] Function: Real-time recording of power generation data (power, voltage, current, etc.);

[0129] Model: WavePower-MonitorV2.0 (Original equipment for power generation unit);

[0130] The core parameters include:

[0131] Measurement parameters: Real-time power generation: 0~2000KW(AC); Output voltage: 0~690V(three-phase); Output current: 0~1600A; Frequency: 50 / 60HZ(±0.5HZ);

[0132] Accuracy: Power: ±0.5%FS (0.2S accuracy); Voltage / Current: ±0.2%FS;

[0133] Sampling frequency: 1 time / second (supports millisecond-level synchronous sampling);

[0134] Communication interfaces: Industrial Ethernet (IEEE 802.3); CAN bus (J1939 protocol);

[0135] Integrated features: Built-in edge unit supports local data preprocessing (noise reduction, filtering); hard-wired linkage with power generation device controller (PLC); Deployment method: embedded in the power conversion system (PCS) of the wave energy power generation device, directly collecting power generation circuit data.

[0136] In this embodiment, S2 includes the following steps:

[0137] S21. Transmit the preprocessed wave energy generation dataset through a communication network. Data is transmitted from edge computing devices to the central control system;

[0138] S22, Wave energy generation data transmitted to the central control system The wave energy generation dataset is categorized and stored, and then allocated to the storage module:

[0139]

[0140] Among them, M i S represents the storage module number to which the i-th data record is allocated. jThis represents the data feature space of storage module j, where j = 1, 2, 3 correspond to wave characteristic data, real-time power generation data, and load demand data, respectively. w represents the i-th data record. j The weight parameters of storage module j depend on the current module's load capacity and response priority;

[0141] S23, Based on wave characteristic data Wave periodicity characteristic data C is extracted using time series analysis. w ={T c H c}:

[0142]

[0143] Among them, T c The primary period of a wave is represented by its frequency ω. k The reciprocal of H is obtained. c Indicates the main wave height, expressed as wave height H. k The root mean square value is calculated, where N represents the total number of samples in the wave characteristic data, and ω k and H k These are the frequency and wave height of the k-th wave, respectively;

[0144] S24, Based on real-time power generation data Calculate power generation fluctuation trend data B using statistical analysis methods. p ={μ p ,σ p}:

[0145]

[0146] Where, μ p σ represents the average value of electricity generated. p P(t) represents the fluctuation range of power generation, P(t) represents the real-time power generation at time t, and T represents the total time length of power generation data recording.

[0147] In this embodiment, S3 includes the following steps:

[0148] S31. Construct a power generation supply model G(t) using real-time power generation data, wave periodicity characteristic data, and fluctuation trend data:

[0149]

[0150] Where G(t) represents the power generation supply capacity at time t, α, β, γ are weighting factors used to balance the impact of real-time power generation, wave periodicity characteristics, and power generation fluctuation trends on the power generation supply model, and H c and T cThese represent the main wave height and main period, respectively, σ p This refers to the fluctuation range of power generation.

[0151] S32. Construct a load demand model L(t) by combining load demand data and energy storage device status data:

[0152]

[0153] Where L(t) represents the actual load demand at time t, E c E represents the current remaining energy of the energy storage device. m E represents the maximum capacity of the energy storage device. m This is an energy storage impact factor used to reflect the ability of energy storage devices to reduce load demand.

[0154] S33. Calculate the load demand priority P based on the power generation supply model G(t) and the load demand model L(t). l (t):

[0155]

[0156] Among them, P l (t) represents the load demand priority at time t, and ∈ is a positive decimal to prevent the denominator from being zero;

[0157] S34, Prioritize load demand P l (t) Classify according to the preset priority threshold θ to form a load priority list P. list :

[0158] P list ={(t i ,P l (t i ))∣P l (t i )≥θ};

[0159] Among them, P list t represents the set of load demand items whose priority meets the threshold. i θ represents the time point i, and θ represents the minimum threshold for priority, used to filter high-priority load demands.

[0160] In this embodiment, S4 includes the following steps:

[0161] S41, Based on the load demand priority list P list Establish a multi-objective optimization function F based on the real-time power generation supply capacity G(t). multi The multi-objective optimization function minimizes the impact of fluctuations and energy storage operating costs, while simultaneously optimizing load coverage.

[0162]

[0163] Among them, F multi The sum of the multi-objective optimization function is represented by w1, w2, and w3, which are weighting factors of the optimization objectives, used to balance supply and demand errors, energy storage costs, and load coverage. a(t) represents the proportion of power generation allocated to the load at time t. out (t) represents the discharge power of the energy storage device at time t, S in (t) represents the charging power of the energy storage device at time t;

[0164] In S41, the volatility of power generation is an inherent characteristic of wave energy, which poses a challenge to the stability of power supply to the load. Therefore, the first measure reflects the degree of supply-demand balance by measuring the error between power generation supply and load demand.

[0165] The goal is to minimize the error. Energy storage operations lead to energy loss, and frequent charging and discharging of equipment will exacerbate performance degradation. The second term is measured by the ratio of the charging and discharging power of the energy storage device, which constrains the cost of energy storage operations.

[0166] Prioritizing load demand is crucial for stable system operation. The third measure quantifies the proportion of load demand met by the power supply through a minimum value function, with the goal of maximizing load coverage.

[0167] S42. Design a dynamic weight adjustment mechanism to dynamically adjust the weight factors of the optimization function based on load demand priority and power generation fluctuation trend data:

[0168]

[0169] Wherein, κ1, κ2, κ3 are the initial weighting factors;

[0170] S43. Initialize the population solution using the bitter fish optimization algorithm, including the power generation allocation ratio a(t) and the energy storage device discharge power S. out (t) and the charging power S of the energy storage device in (t), and introduce a fluctuation sensitivity factor φ(t) to enhance the diversity of population solutions:

[0171]

[0172] The population solution is initialized as follows:

[0173] a i (t)=φ(t)·rand(0,1);

[0174]

[0175] Where φ(t) represents the fluctuation sensitivity factor, which adjusts the search range of the population solution based on wave periodicity and fluctuation amplitude, and rand(a,b) represents the random number generated in the interval [a,b].

[0176] S44. Perform global search and local optimization on the initialized population solution, and trigger population reconstruction during periods of high volatility based on the jumping mechanism of the bitter fish algorithm:

[0177]

[0178] Where randn(μ, σ) represents a Gaussian random variable with mean μ and standard deviation σ;

[0179] Population reconstruction dynamically adjusts the search direction through a fluctuation-sensitive factor φ(t);

[0180] S45. The iterative update and optimization results ultimately yield the optimal power generation allocation ratio a. * (t), Discharge power of energy storage device and energy storage device charging power Based on the optimization results, energy storage scheduling plans and load scheduling plans are generated.

[0181] In this embodiment, S5 includes the following steps:

[0182] S51, Based on Energy Storage Dispatch Plan The optimal result of the load scheduling plan a * (t), defining the selection criteria for energy storage priority mode, output priority mode, and hybrid mode:

[0183]

[0184] Where M(t) represents the mode selection at time t, 1 is the energy storage priority mode, 2 is the output priority mode, 3 is the hybrid mode, and δ is the energy storage state threshold, which represents the key value of the charging state of the energy storage device, and its range is [0,1].

[0185] S52. In the energy storage priority mode, the wave energy power generation system prioritizes charging the energy storage device and dynamically adjusts the power generation supply ratio.

[0186] S53. In the output priority mode, the wave energy power generation system prioritizes meeting the load demand and uses energy storage devices to supplement the insufficient power supply.

[0187] S54. In hybrid mode, the wave energy power generation system meets the load demand while using the remaining power generation capacity to charge the energy storage device and dynamically adjusts the power generation distribution.

[0188] In this embodiment, S6 includes the following steps:

[0189] S61. Calculate the target charging and discharging power S of the energy storage device based on wave energy generation data G(t) and load demand model L(t). target (t):

[0190]

[0191] Among them, S target (t) represents the target charging and discharging power of the energy storage device at time t, E c and E m These represent the current remaining energy and maximum capacity of the energy storage device, respectively.

[0192] S62. Calculate the actual charging and discharging power S based on the operating status of the energy storage device. actual (t):

[0193]

[0194] Among them, S actual (t) represents the actual charging and discharging power of the energy storage device at time t, R in} represents the maximum charging rate of the energy storage device, R out This indicates the maximum discharge rate of the energy storage device;

[0195] S63. Update the operating status of the energy storage device, including the current remaining energy E. c and charge / discharge modes:

[0196]

[0197] in, M represents the remaining energy of the energy storage device at the next moment, Δt represents the time interval, and M represents the energy of the device at the next moment. s (t) represents the charging and discharging mode of the energy storage device, where 1 is the charging mode, -1 is the discharging mode, and 0 is the standby mode;

[0198] S64. Monitor the operating status of the energy storage device in real time and adjust the operating strategy based on the anomaly detection mechanism:

[0199] like Then the charging power is limited;

[0200] like This limits the discharge power.

[0201] A dynamic energy management system based on wave energy generation data, used to execute a dynamic energy management method based on wave energy generation data, includes the following modules:

[0202] The wave energy data acquisition module is used to acquire wave characteristic data, real-time power generation data, and load demand data through a sensor network, and upload them to the edge computing device in real time to complete data preprocessing, including data cleaning, noise reduction, and formatting, to generate a preprocessed wave energy power generation dataset.

[0203] The data transmission and storage module transmits the pre-processed wave energy power generation dataset to the central control system through a communication network, and classifies and stores the data, including wave characteristic data storage, power generation data storage and load demand data storage.

[0204] The data analysis and feature extraction module is used to analyze the stored data, extract wave periodicity feature data and fluctuation trend data, and generate a power generation characteristic model and its dynamic change trend.

[0205] The load demand assessment module combines real-time power generation data, wave periodicity characteristic data, and fluctuation trend data with load demand data and energy storage device status data to calculate and generate a load demand model. It also dynamically assesses the priority of load demand and forms a priority list.

[0206] The optimization scheduling module uses the "bitter fish" optimization algorithm to allocate energy to the wave energy power generation system based on the load demand priority list, calculates the energy storage scheduling plan and the load scheduling plan, and dynamically adjusts the parameters of the optimization algorithm to adapt to the periodic and random changes of wave energy.

[0207] The mode selection module, in conjunction with the energy storage scheduling plan and the load scheduling plan, selects the optimal mode from the energy storage priority mode, output priority mode or hybrid mode based on the energy storage device status and power generation capacity, and dynamically adjusts the proportion of energy output.

[0208] The energy storage operation control module controls the charging and discharging operations of the energy storage device based on real-time wave energy generation data and load demand model, and adjusts its charging and discharging power according to the operating status of the energy storage device to avoid overcharging or over-discharging, while ensuring the operation of the energy storage device under different load demands.

[0209] The real-time monitoring and feedback module monitors the operating status of the wave energy power generation system, energy storage device and load equipment in real time, collects feedback data and transmits it to the optimization scheduling module and mode selection module, dynamically adjusts the energy management strategy, and forms a closed-loop control of the system.

[0210] The system coordination and communication module is used to coordinate the operating status of wave energy generation devices, energy storage devices, and load equipment, and to ensure real-time data exchange and collaborative computing between the modules through communication protocols.

[0211] Example 1:

[0212] In an example, during the operation of a wave energy power station in a coastal city, in order to meet the electricity demand of residents on nearby islands and improve power generation efficiency, the implementers conducted a complete test and application of the dynamic energy management method for wave energy power generation data on a certain day in November 2024.

[0213] At 9:00 AM on the day the test began, wave data recorded by sensors showed a wave height of 2.4 meters, a wave period of 8 seconds, and a real-time power generation of 1450 kilowatts from the wave energy power generation device. At this time, the island's load demand was 1700 kilowatts. The system detected that the high priority items in the load demand priority list were "daily power supply for island residents" and "operation of marine aquaculture equipment," with demands of 800 kilowatts and 600 kilowatts, respectively. The central control system, based on the scheduling plan generated by the Kuyu optimization algorithm, showed that the current selected mode was "output priority mode," prioritizing the use of power generation to meet load demand. At the same time, the energy storage device supplemented the remaining demand, discharging 250 kilowatts to ensure stable power supply to the load.

[0214] At 10:30 AM, wave data recordings showed that the wave height rose to 2.8 meters, the wave period remained at 8 seconds, and the real-time power generation increased to 1900 kilowatts. The system detected that the load demand had decreased to 1500 kilowatts, of which the demand for "daily power supply for island residents" was 700 kilowatts and the demand for "operational equipment for tourist attractions" was 600 kilowatts. The central control system switched to "hybrid mode," allocating 1100 kilowatts to the load while charging the energy storage device at a power of 800 kilowatts. At this time, the remaining capacity of the energy storage device was 12 megawatt-hours, and the system monitoring showed that the charging efficiency reached 95%.

[0215] At 3:00 PM, wave data monitoring recorded a decrease in wave height to 1.5 meters, a shortening of the wave period to 6 seconds, and a reduction in real-time power generation to 1100 kW. The island's load demand increased to 1900 kW, including a 500 kW demand from newly added "marine scientific research equipment." The system detected a remaining capacity of 15 MWh in the energy storage device and generated a scheduling plan using "energy storage priority mode" to supplement the load shortage by discharging the energy storage device. System monitoring showed that the energy storage device discharged at a power of 700 kW, while the power generation device supplied 1100 kW, meeting all load demands.

[0216] Throughout the test, the system's real-time monitoring and feedback module recorded key data:

[0217] 9:00-10:30 AM, energy storage device charging status

[0218] Charging power: 800 kW;

[0219] Charging time: 1 hour and 30 minutes;

[0220] Energy storage capacity change: from 10 MWh to 12 MWh.

[0221] From 3:00 PM to 5:00 PM, the energy storage device is in discharge mode.

[0222] Discharge power: 700 kilowatts;

[0223] Discharge duration: 2 hours;

[0224] Energy storage capacity change: from 15 MWh to 13 MWh.

[0225] After the test, the implementer compared the method of the present invention with the traditional method and recorded the data in Table 1 below:

[0226] Table 1 Comparison of power generation satisfaction rates between the method of this invention and the traditional method at different time periods.

[0227]

[0228] As shown in Table 1 above, this invention achieves precise matching of power generation and load demand under different load and power generation conditions through dynamic mode switching and intelligent energy storage regulation, avoiding energy waste and significantly improving energy utilization efficiency compared to traditional methods. In situations of supply-demand imbalance, the method of this invention can adjust the charging and discharging operation of the energy storage device in real time, reducing the impact of power supply fluctuations on the load and maintaining a 100% satisfaction rate, significantly better than the fluctuation satisfaction rate of traditional methods. By employing an improved "bitter fish" optimization algorithm combined with real-time data analysis, it dynamically generates energy storage scheduling plans and load scheduling plans, adapting to complex wave environments and variable load scenarios. Traditional methods lack such intelligent regulation capabilities and have significant limitations.

[0229] Through the above tests, the implementers found that the method of the present invention has significant advantages in load demand priority adjustment, dynamic charging and discharging management of energy storage devices, and optimization of energy distribution strategies. It can effectively improve power supply stability and energy utilization efficiency under complex wave conditions and dynamic load demands.

[0230] This invention employs an improved "bitter fish" optimization algorithm, combining the periodic characteristics and random fluctuations of wave energy generation. Through a dynamic weight adjustment mechanism and the introduction of a fluctuation-sensitive factor, it achieves efficient matching between power generation supply and load demand. The improved "bitter fish" optimization algorithm can dynamically adjust the energy allocation strategy based on real-time changes in wave energy data, significantly reducing the impact of supply-demand imbalance on system stability under complex wave conditions. Simultaneously, it supports flexible switching between energy storage priority, output priority, and hybrid modes, ensuring efficient system operation in various application scenarios.

[0231] This invention constructs a complete dynamic feedback closed-loop control system through the charging and discharging control and real-time operation status monitoring of the energy storage device. By real-time evaluation of the load demand model and dynamic adjustment of the priority list, combined with the execution of the energy storage scheduling plan and the load scheduling plan, it realizes precise linkage between the energy storage device and the power generation system. Compared with traditional energy storage control strategies, this invention can adjust the charging and discharging mode of the energy storage device according to real-time data, effectively avoiding overcharging or over-discharging problems of the energy storage device and optimizing the operating efficiency of the energy storage system.

[0232] This invention constructs an integrated energy management system architecture encompassing data acquisition, transmission, storage, analysis, and scheduling. It can capture wave energy characteristic data, power generation data, and load demand data in real time, generating high-precision power supply and load demand models. Through the intelligent analysis and optimization scheduling modules of the central control system, it rapidly generates energy storage scheduling plans and load scheduling plans. Combined with a dynamic mode selection module, it optimizes energy allocation. This data-driven architecture enables the system to quickly respond to fluctuations in wave energy generation, improving the efficiency and accuracy of energy allocation decisions. It significantly enhances the system's adaptability to volatility and load coverage in complex scenarios, meeting the needs of modern marine energy applications.

[0233] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A dynamic energy management method based on wave energy generation data, characterized in that, Includes the following steps: S1. Obtain the wave energy power generation dataset and transmit the wave energy power generation dataset to the edge computing device for preprocessing; S2. The preprocessed wave energy power generation dataset is transmitted to the central control system through a communication network, and the wave energy power generation data is classified, stored and analyzed to generate wave periodicity characteristic data and fluctuation trend data. S3. Based on real-time power generation data, wave periodicity characteristic data, and fluctuation trend data, combined with load demand data and energy storage device status, generate a load demand model and assess the priority of current load demand; S3 includes the following steps: S31. Construct a power generation supply model G(t) using real-time power generation data, wave periodicity characteristic data, and fluctuation trend data: ； Where G(t) represents the power generation supply capacity at time t. These are weighting factors used to balance the impact of real-time power generation, wave periodicity characteristics, and power generation fluctuation trends on the power generation supply model. and These are the main wave height and the main period, respectively. For the fluctuation range of power generation, This represents the real-time power generation data after cleaning and noise reduction. S32. Construct a load demand model L(t) by combining load demand data and energy storage device status data: ； Where L(t) represents the actual load demand at time t. This indicates the current remaining energy of the energy storage device. Indicates the maximum capacity of the energy storage device. This is an energy storage impact factor used to reflect the ability of energy storage devices to reduce load demand. This represents the load demand data after cleaning and noise reduction. S33. Calculate load demand priority based on the power generation supply model G(t) and the load demand model L(t). : ； in, This indicates the priority of load demand at time t. To prevent positive decimals with a denominator of zero; S34. Prioritize load demands According to the preset priority threshold Classify and form a load priority list. : ； in, This represents the set of load demand items whose priority meets the threshold. This represents the time point i. The minimum threshold indicating priority is used to filter high-priority load demands. S4. Based on the dynamic load demand assessment results, the improved bitter fish optimization algorithm is used to allocate energy to the wave energy power generation system and generate energy storage scheduling plan and load scheduling plan; S4 includes the following steps: S41, Load Demand Priority List Establish a multi-objective optimization function for the real-time power generation supply capacity G(t). The multi-objective optimization function minimizes the impact of fluctuations and energy storage operating costs, while simultaneously optimizing load coverage. }； in, This represents the total value of the multi-objective optimization function. The weighting factors for the optimization objective are used to balance supply and demand errors, energy storage costs, and load coverage. This represents the proportion of power generation allocated to the load at time t. This represents the discharge power of the energy storage device at time t. This represents the charging power of the energy storage device at time t; S42. Design a dynamic weight adjustment mechanism to dynamically adjust the weight factors of the optimization function based on load demand priority and power generation fluctuation trend data: ； in, These are the initial weighting factors; S43. Initialize the population solution using the bitter fish optimization algorithm, including the power generation allocation ratio a(t) and the energy storage device discharge power. and energy storage device charging power And introduce volatility-sensitive factors Enhancing the diversity of population solutions: ； The population solution is initialized as follows: ； ； ； in, This represents the average amount of electricity generated. This represents a fluctuation sensitivity factor, which adjusts the search range of the population solution based on wave periodicity and fluctuation amplitude. This represents a random number generated in the interval [a, b]. S44. Perform global search and local optimization on the initialized population solution, and trigger population reconstruction during periods of high volatility based on the jumping mechanism of the bitter fish algorithm: ； in, The mean is Standard deviation is Gaussian random variables; Population reconstruction through fluctuation-sensitive factors Dynamically adjust the search direction; S45. The optimal power generation allocation ratio is finally obtained by iteratively updating and optimizing the results. Discharge power of energy storage device and energy storage device charging power Based on the optimization results, energy storage scheduling plans and load scheduling plans are generated; S5. Combining the energy storage dispatch plan and the load dispatch plan, select one of the following modes: energy storage priority mode, output priority mode, or hybrid mode, and dynamically adjust the energy output of the wave energy power generation system in the selected mode; S6. Control the charging and discharging operations of the energy storage device based on the current wave energy generation data and load demand model, and adjust the operating status of the energy storage device in real time.

2. The dynamic energy management method based on wave energy generation data according to claim 1, characterized in that, S1 includes the following steps: S11. Obtain wave characteristic data by using ocean wave sensors deployed in the wave energy power generation system. ; S12. Record the power generation data in real time through the monitoring device on the wave energy power generation device. ; S13. Obtain load demand data through the load monitoring system. ; S14 constructs a wave energy power generation dataset, which time-series correlates wave characteristic data, real-time power generation data, and load demand data, forming a unified wave energy power generation dataset indexed by timestamps: ； S15 inputs the constructed wave energy power generation dataset D into the edge computing device for data cleaning, noise reduction, and formatting to generate a preprocessed wave energy power generation dataset: ； in, This represents the wave characteristics data after cleaning and noise reduction. This represents the real-time power generation data after cleaning and noise reduction. This represents the load demand data after cleaning and noise reduction.

3. The dynamic energy management method based on wave energy generation data according to claim 2, characterized in that, S2 includes the following steps: S21. Transmit the preprocessed wave energy generation dataset through a communication network. Data is transmitted from edge computing devices to the central control system; S22, Wave energy generation data transmitted to the central control system The wave energy generation dataset is categorized and stored, and then allocated to the storage module: ； in, This indicates the storage module number to which the i-th data record is assigned. This represents the data feature space of storage module j, where j=1,2,3 correspond to wave characteristic data, real-time power generation data, and load demand data, respectively. This represents the i-th data record. The weight parameters of storage module j depend on the current module's load capacity and response priority; S23, Based on wave characteristic data Wave periodicity characteristic data were extracted using time series analysis methods. : ； ； in, The primary period of a wave is represented by its frequency. The reciprocal is obtained. Indicates the main wave height, expressed through wave height. The root mean square value is calculated, where N represents the total number of samples in the wave characteristic data. and These are the frequency and wave height of the k-th wave, respectively; S24, Based on real-time power generation data Calculate power generation fluctuation trend data using statistical analysis methods. : ； ； in, This represents the average amount of electricity generated. P(t) represents the fluctuation range of power generation, P(t) represents the real-time power generation at time t, and T represents the total time length of power generation data recording.

4. The dynamic energy management method based on wave energy generation data according to claim 1, characterized in that, S5 includes the following steps: S51, Based on Energy Storage Dispatch Plan The optimal result of the load scheduling plan Define the selection criteria for energy storage priority mode, output priority mode, and hybrid mode: ； Where M(t) represents the mode selection at time t, 1 for energy storage priority mode, 2 for output priority mode, and 3 for hybrid mode. The energy storage state threshold is a key value representing the charging state of the energy storage device, ranging from [0,1]. S52. In the energy storage priority mode, the wave energy power generation system prioritizes charging the energy storage device and dynamically adjusts the power generation supply ratio. S53. In the output priority mode, the wave energy power generation system prioritizes meeting the load demand and uses energy storage devices to supplement the insufficient power supply. S54. In hybrid mode, the wave energy power generation system meets the load demand while using the remaining power generation capacity to charge the energy storage device and dynamically adjusts the power generation distribution.

5. A dynamic energy management method based on wave energy generation data according to claim 1, characterized in that, S6 includes the following steps: S61. Calculate the target charging and discharging power of the energy storage device based on wave energy generation data G(t) and load demand model L(t). : ； in, This represents the target charging and discharging power of the energy storage device at time t. and These represent the current remaining energy and maximum capacity of the energy storage device, respectively. S62. Calculate the actual charging and discharging power based on the operating status of the energy storage device. : ； in, This represents the actual charging and discharging power of the energy storage device at time t. This indicates the maximum charging power of the energy storage device. This indicates the maximum discharge power of the energy storage device; S63. Update the operating status of the energy storage device, including the current remaining energy. and charge / discharge modes: ； ； in, This indicates the remaining energy of the energy storage device at the next moment. Indicates time interval, This indicates the charging and discharging mode of the energy storage device: 1 for charging mode, -1 for discharging mode, and 0 for standby mode. S64. Monitor the operating status of the energy storage device in real time and adjust the operating strategy based on the anomaly detection mechanism: ； 。 6. A dynamic energy management system based on wave energy generation data, used to execute the dynamic energy management method based on wave energy generation data as described in any one of claims 1-5, characterized in that, Includes the following modules: The wave energy data acquisition module is used to acquire wave characteristic data, real-time power generation data, and load demand data through a sensor network, and upload them to the edge computing device in real time to complete data preprocessing, including data cleaning, noise reduction, and formatting, to generate a preprocessed wave energy power generation dataset. The data transmission and storage module transmits the pre-processed wave energy power generation dataset to the central control system through a communication network, and classifies and stores the data, including wave characteristic data storage, power generation data storage and load demand data storage. The data analysis and feature extraction module is used to analyze the stored data, extract wave periodicity feature data and fluctuation trend data, and generate a power generation characteristic model and its dynamic change trend. The load demand assessment module combines real-time power generation data, wave periodicity characteristic data, and fluctuation trend data with load demand data and energy storage device status data to calculate and generate a load demand model. It also dynamically assesses the priority of load demand and forms a priority list. The optimization scheduling module uses the "bitter fish" optimization algorithm to allocate energy to the wave energy power generation system based on the load demand priority list, calculates the energy storage scheduling plan and the load scheduling plan, and dynamically adjusts the parameters of the optimization algorithm to adapt to the periodic and random changes of wave energy. The mode selection module, in conjunction with the energy storage scheduling plan and the load scheduling plan, selects the optimal mode from the energy storage priority mode, output priority mode or hybrid mode based on the energy storage device status and power generation capacity, and dynamically adjusts the proportion of energy output. The energy storage operation control module controls the charging and discharging operations of the energy storage device based on real-time wave energy generation data and load demand model, and adjusts its charging and discharging power according to the operating status of the energy storage device to avoid overcharging or over-discharging, while ensuring the operation of the energy storage device under different load demands. The real-time monitoring and feedback module monitors the operating status of the wave energy power generation system, energy storage device and load equipment in real time, collects feedback data and transmits it to the optimization scheduling module and mode selection module, dynamically adjusts the energy management strategy, and forms a closed-loop control of the system. The system coordination and communication module is used to coordinate the operating status of wave energy generation devices, energy storage devices, and load equipment, and to ensure real-time data exchange and collaborative computing between the modules through communication protocols.

Images